© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 103715
    Prev
    Next
    INDEX
    Explanations

    requirements, satisfaction, or quotas

    np_acts-logits-general · gemini-2.5-flash-lite

    data structuring and specific domains

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    dDevice
    0.52
     వ్యక్
    0.48
    náv
    0.44
    чется
    0.43
     moverse
    0.42
    alé
    0.42
     olacaktır
    0.42
    ⃖
    0.42
    arán
    0.41
     Nutzen
    0.41
    POSITIVE LOGITS
     soddisf
    0.48
    #
    0.47
     requirements
    0.47
    満足
    0.47
    %
    0.46
     standings
    0.46
     requirement
    0.44
     level
    0.44
     satisfaction
    0.44
     quotas
    0.44
    Activations Density 0.006%

    No Known Activations